Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to connections or associations between concepts or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     voks
    -0.18
    ync
    -0.17
     allergy
    -0.15
    lah
    -0.15
    wards
    -0.15
    rapy
    -0.15
    etics
    -0.14
    tes
    -0.14
    weg
    -0.14
    meer
    -0.14
    POSITIVE LOGITS
     knot
    0.29
     knots
    0.27
     Knot
    0.26
    breaker
    0.23
     tie
    0.22
     tying
    0.22
    tie
    0.20
    breaking
    0.19
     tied
    0.19
    backs
    0.18
    Act Density 0.016%

    No Known Activations